Skip to main navigation Skip to search Skip to main content

UAV Swarm Attack-Defense Confrontation Based on Multi-agent Reinforcement Learning

  • Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

31 Scopus citations

Abstract

This paper studies the problem of UAV swarm attack-defense confrontation, which can be viewed as an extension of defending territory game. In this problem, a swarm of intruder UAVs attempt to invade into a territory, which is guarded by a swarm of defender UAVs. This problem is a great challenge to traditional methods. To deal with it, a multi-agent deep reinforcement learning approach is proposed, which is based on the Multi-Agent Deep Deterministic Policy Gradient algorithm (MADDPG). A simulation platform is developed which takes account of UAV flight constraints and simulates a real flight environment. To study the performance of the proposed algorithm, we compare it with DDPG. Experimental results show that the UAVs using the MADDPG algorithm can learn better strategies and achieve better performance.

Original languageEnglish
Title of host publicationAdvances in Guidance, Navigation and Control - Proceedings of 2020 International Conference on Guidance, Navigation and Control, ICGNC 2020
EditorsLiang Yan, Haibin Duan, Xiang Yu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages5599-5608
Number of pages10
ISBN (Print)9789811581540
DOIs
StatePublished - 2022
EventInternational Conference on Guidance, Navigation and Control, ICGNC 2020 - Tianjin, China
Duration: 23 Oct 202025 Oct 2020

Publication series

NameLecture Notes in Electrical Engineering
Volume644 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Guidance, Navigation and Control, ICGNC 2020
Country/TerritoryChina
CityTianjin
Period23/10/2025/10/20

Keywords

  • Confrontation
  • Reinforcement Learning
  • UAV swarm

Fingerprint

Dive into the research topics of 'UAV Swarm Attack-Defense Confrontation Based on Multi-agent Reinforcement Learning'. Together they form a unique fingerprint.

Cite this